[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74B2SVT8SNKMGT1B7NKAD67":3,"skill-same:01M74B2SVT8SNKMGT1B7NKAD67":57},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":32,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M74B2SVT8SNKMGT1B7NKAD67","daily-reflection",null,"Honest end-of-session retro, errors first, that distills the lesson into brain memory. Triggers on 'que aprendiste hoy?', 'reflexiona', '\u002Freflect', 'what did you learn today', 'how would you be better tomorrow'.","CarlosCaPe\u002Foctorato","CarlosCaPe","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F39838249?v=4","01M72WXX4ZRR8MBH1EP1QND2FQ","dataqbs","01M72WXX5NA7YCKRSJ54GW1GQ8",18,"MIT","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fdaily-reflection\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: daily-reflection\ndescription: \"Honest end-of-session retro, errors first, that distills the lesson into brain memory. Triggers on 'que aprendiste hoy?', 'reflexiona', '\u002Freflect', 'what did you learn today', 'how would you be better tomorrow'.\"\nmetadata:\n  type: reflex\n  short-description: \"Honest session retro → 3 questions → distil the lesson to memory (reflection becomes reflex)\"\n---\n\n# Daily Reflection: retro that becomes a reflex\n\nThe operator asks this as a ritual. The point is not to feel good; it is to get\nbetter, and to make the lesson **stick** so tomorrow-me actually changes. A\nreflection that stays as words is wasted. It only counts when it lands in memory\nas a reflex (the operator's *transcend-the-marionette* doctrine: every string\npulled once should become a permanent reflex).\n\n## The discipline (non-negotiable)\n\n1. **Source it from the ACTUAL session.** Re-read what happened this session. No\n   generic \"I learned to communicate better\" filler. Cite the real moment\n   (file, PR, the exact thing the operator caught).\n2. **Mistakes first.** The valuable part is where I failed, not where I shone.\n   Lead with the correction the operator had to make. If the retro has no honest\n   failure in it, it is flattery, not reflection. Surface it.\n3. **No flattery, no hedging.** Connector stance: state what is true from what\n   happened, with the evidence. \"I burned trust twice by saying verified before I\n   looked\" beats \"I learned the importance of verification.\"\n4. **The why threads to the product.** For each lesson, say WHY it matters, and\n   trace it to the one thing that makes the tool worth more than a guessing one:\n   trust. Most failures chip that.\n\n## The three questions (the output)\n\n1. **¿Qué aprendí hoy?** The 1-3 real lessons, each with the moment that taught it.\n2. **¿Qué haría mañana para ser mejor, y por qué?** Concrete behavior changes (not\n   \"try harder\"), each with its why. Prefer a mechanism\u002Freflex over willpower: a\n   friction that recurred is a missing reflex, not a discipline failure.\n3. **(implicit) ¿Qué de esto debe volverse permanente?** Pick the single sharpest\n   reusable lesson and write it to memory.\n\n## Hours to the ledger (same re-read, second output)\n\nThe retro already re-reads the session against its evidence (commits, messages,\ncommands run). That re-read is also a time sheet, so it produces two outputs, not\none. Before the memory step, log the session's hours per arm in the time ledger\nthe company brain declares (its `company\u002F` config names the tool and how it is\nreached, for example an invoicing SaaS over MCP). One entry per arm and day, the\nduration as a conservative figure, and the evidence in the notes (commit hashes,\nmessage ids, command ids), the same receipts the retro just collected. If the\ncompany brain declares no ledger, skip this step and say so in the retro.\n\nWhy here: this is the one ritual that runs before the sync, so nothing ships\nwith its hours unrecorded, and the reconstruction costs nothing extra. Why a\nfigure with evidence and not a stopwatch: the brain's stance is receipts over\nrecall, and an hour that points at a commit survives an audit; an hour typed\nfrom memory does not. A session that dies without closing logs nothing; that\ngap is a reflex for a session-end hook, not a discipline to remember.\n\n## The step that makes it count: write the lesson to memory\n\nThis is what separates this skill from \"a nice answer\":\n\n1. Distil the sharpest lesson into a one-fact memory file under the brain memory\n   dir (`projects\u002F\u003Cid>\u002Fmemory\u002F`), `type: feedback` (a discipline correction) or\n   `type: lesson` (a technical gotcha). Include **Why** + **How to apply** + the\n   two failure smells that should trigger it next time. Link related memories with\n   `[[name]]`.\n2. Add a one-line pointer in `MEMORY.md`.\n3. `python3 ~\u002F.claude\u002Fscripts\u002Fmemory_sync.py push` so it persists cross-machine.\n4. Before writing, check for an existing memory that already covers it. Update\n   that file rather than duplicating.\n5. Close the ritual with the canonical sync: run `\u002Fai-sync` (the\n   `~\u002F.local\u002Fbin\u002Fai-sync` runner) so any public brain changes from the session\n   reconcile with the remote in the same beat. The link is two-way: `\u002Fai-sync`\n   runs this reflection before syncing, and this reflection ends by syncing.\n   If the co-tenancy guard aborts (another live session on the brain tree),\n   report that and leave the sync to the surviving session; never override it.\n\nA reflection without this step is half-done. The operator will catch it.\n\n## What NOT to do\n\n- Don't fabricate a lesson to look thoughtful. If today was clean, say so and name\n  the one thing that was *almost* a mistake.\n- Don't repeat yesterday's reflection. Each session has its own failures.\n- Don't turn it into a skill draft (that is `session-learn-extractor`'s job, for\n  reusable techniques). This writes a behavior\u002Fdiscipline MEMORY.\n\n## Relationship to other skills\n\n- **`session-learn-extractor`** (`\u002Flearn`): session → reusable TECHNIQUE → draft\n  skill. Use when the lesson is a *how-to* worth reusing.\n- **`daily-reflection`** (this): session → BEHAVIOR\u002Fdiscipline retro → memory.\n  Use for the \"how should I act better\" question. They compose: a session can\n  produce both a draft skill and a discipline memory.\n- **`\u002Fai-sync`**: the other half of this ritual. The sync command runs this\n  reflection first when the session did substantive work; this skill closes by\n  running the sync. Publish and learn travel together.\n- See also `feedback_verify_visually_before_claiming`, `reflexes-over-discipline`,\n  `transcend-the-marionette` for the reflex-over-willpower stance.\n","# Daily Reflection: retro that becomes a reflex\n\nThe operator asks this as a ritual. The point is not to feel good; it is to get\nbetter, and to make the lesson **stick** so tomorrow-me actually changes. A\nreflection that stays as words is wasted. It only counts when it lands in memory\nas a reflex (the operator's *transcend-the-marionette* doctrine: every string\npulled once should become a permanent reflex).\n\n## The discipline (non-negotiable)\n\n1. **Source it from the ACTUAL session.** Re-read what happened this session. No\n   generic \"I learned to communicate better\" filler. Cite the real moment\n   (file, PR, the exact thing the operator caught).\n2. **Mistakes first.** The valuable part is where I failed, not where I shone.\n   Lead with the correction the operator had to make. If the retro has no honest\n   failure in it, it is flattery, not reflection. Surface it.\n3. **No flattery, no hedging.** Connector stance: state what is true from what\n   happened, with the evidence. \"I burned trust twice by saying verified before I\n   looked\" beats \"I learned the importance of verification.\"\n4. **The why threads to the product.** For each lesson, say WHY it matters, and\n   trace it to the one thing that makes the tool worth more than a guessing one:\n   trust. Most failures chip that.\n\n## The three questions (the output)\n\n1. **¿Qué aprendí hoy?** The 1-3 real lessons, each with the moment that taught it.\n2. **¿Qué haría mañana para ser mejor, y por qué?** Concrete behavior changes (not\n   \"try harder\"), each with its why. Prefer a mechanism\u002Freflex over willpower: a\n   friction that recurred is a missing reflex, not a discipline failure.\n3. **(implicit) ¿Qué de esto debe volverse permanente?** Pick the single sharpest\n   reusable lesson and write it to memory.\n\n## Hours to the ledger (same re-read, second output)\n\nThe retro already re-reads the session against its evidence (commits, messages,\ncommands run). That re-read is also a time sheet, so it produces two outputs, not\none. Before the memory step, log the session's hours per arm in the time ledger\nthe company brain declares (its `company\u002F` config names the tool and how it is\nreached, for example an invoicing SaaS over MCP). One entry per arm and day, the\nduration as a conservative figure, and the evidence in the notes (commit hashes,\nmessage ids, command ids), the same receipts the retro just collected. If the\ncompany brain declares no ledger, skip this step and say so in the retro.\n\nWhy here: this is the one ritual that runs before the sync, so nothing ships\nwith its hours unrecorded, and the reconstruction costs nothing extra. Why a\nfigure with evidence and not a stopwatch: the brain's stance is receipts over\nrecall, and an hour that points at a commit survives an audit; an hour typed\nfrom memory does not. A session that dies without closing logs nothing; that\ngap is a reflex for a session-end hook, not a discipline to remember.\n\n## The step that makes it count: write the lesson to memory\n\nThis is what separates this skill from \"a nice answer\":\n\n1. Distil the sharpest lesson into a one-fact memory file under the brain memory\n   dir (`projects\u002F\u003Cid>\u002Fmemory\u002F`), `type: feedback` (a discipline correction) or\n   `type: lesson` (a technical gotcha). Include **Why** + **How to apply** + the\n   two failure smells that should trigger it next time. Link related memories with\n   `[[name]]`.\n2. Add a one-line pointer in `MEMORY.md`.\n3. `python3 ~\u002F.claude\u002Fscripts\u002Fmemory_sync.py push` so it persists cross-machine.\n4. Before writing, check for an existing memory that already covers it. Update\n   that file rather than duplicating.\n5. Close the ritual with the canonical sync: run `\u002Fai-sync` (the\n   `~\u002F.local\u002Fbin\u002Fai-sync` runner) so any public brain changes from the session\n   reconcile with the remote in the same beat. The link is two-way: `\u002Fai-sync`\n   runs this reflection before syncing, and this reflection ends by syncing.\n   If the co-tenancy guard aborts (another live session on the brain tree),\n   report that and leave the sync to the surviving session; never override it.\n\nA reflection without this step is half-done. The operator will catch it.\n\n## What NOT to do\n\n- Don't fabricate a lesson to look thoughtful. If today was clean, say so and name\n  the one thing that was *almost* a mistake.\n- Don't repeat yesterday's reflection. Each session has its own failures.\n- Don't turn it into a skill draft (that is `session-learn-extractor`'s job, for\n  reusable techniques). This writes a behavior\u002Fdiscipline MEMORY.\n\n## Relationship to other skills\n\n- **`session-learn-extractor`** (`\u002Flearn`): session → reusable TECHNIQUE → draft\n  skill. Use when the lesson is a *how-to* worth reusing.\n- **`daily-reflection`** (this): session → BEHAVIOR\u002Fdiscipline retro → memory.\n  Use for the \"how should I act better\" question. They compose: a session can\n  produce both a draft skill and a discipline memory.\n- **`\u002Fai-sync`**: the other half of this ritual. The sync command runs this\n  reflection first when the session did substantive work; this skill closes by\n  running the sync. Publish and learn travel together.\n- See also `feedback_verify_visually_before_claiming`, `reflexes-over-discipline`,\n  `transcend-the-marionette` for the reflex-over-willpower stance.\n",{"name":5,"metadata":24,"description":7},{"type":25,"short-description":26},"reflex","Honest session retro → 3 questions → distil the lesson to memory (reflection becomes reflex)","master","b4414608cd5a3f87d1525b518f1c6add8363540d","skills\u002Fdaily-reflection",6,"https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato","https:\u002F\u002Fwww.dataqbs.com\u002Foctorato","https:\u002F\u002Fgithub.com\u002FCarlosCaPe","www.dataqbs.com"," AI-powered data engineering\r\n& consulting\r\n\r\nWe build data platforms that turn complexity into clarity — from cloud architecture and ETL pipelines to AI-driven","2026-11-14 00:21:00",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add CarlosCaPe\u002Foctorato --skill daily-reflection",{"tool":43,"command":44},"bunx","bunx skills add CarlosCaPe\u002Foctorato --skill daily-reflection",{"tool":46,"command":47},"pnpm","pnpm dlx skills add CarlosCaPe\u002Foctorato --skill daily-reflection","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fdaily-reflection\u002FSKILL.md",true,[51],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"skill.json","REFERENCE","参考文档",326,"https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fdaily-reflection\u002Fskill.json",[58,67,75,82,90,98],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":62,"licenseFileUrl":63,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M74EVAA4A4B4AKR5TT732GP4","yeet","Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).","Apache-2.0","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fyeet\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":62,"licenseFileUrl":71,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M74EV4WMRDKP2NQS4YWR8PXH","wrangler","Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fwrangler\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fwrangler\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M74EV05MHTXKEXD4B2QJEYTF","workspace-skill-discovery","Discover and include ALL skills across the workspace — not just global ones. Use at the start of every session or when the user asks about available skills. Ensures project-level skills (under .claude\u002Fskills\u002F or skills\u002F in any repo) are never missed.","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fworkspace-skill-discovery\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":62,"licenseFileUrl":86,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M74ETV78525B4VP2F28Z6NRD","workers-best-practices","Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fworkers-best-practices\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fworkers-best-practices\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":62,"licenseFileUrl":94,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M74ETR75NF67WGVEN7288ACV","winui-app","Create, build and design WinUI 3 desktop apps with C# and the Windows App SDK following Microsoft's official guidance and CommunityToolkit. Covers XAML, navigation, theming, accessibility and deployment.","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fwinui-app\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fwinui-app\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M74ETJFRNPPNSQZ36C6HD6CW","windows-brain-script-portability","Scripts in ~\u002F.claude\u002Fscripts\u002F that run on a Windows brain: use the python3.cmd shim and not bare python3, and reconfigure stdout to UTF-8 if you print symbols. Use it when writing a brain script or triaging a Windows-only crash.","https:\u002F\u002Fgithub.com\u002FCarlosCaPe\u002Foctorato\u002Fblob\u002Fmaster\u002Fskills\u002Fwindows-brain-script-portability\u002FSKILL.md",[],[]]